共查询到20条相似文献，搜索用时 31 毫秒
1.
《Communications in Soil Science and Plant Analysis》2012,43(8):925-938
Soil organic matter is a very important component of soil that supports the sustainability and quality in all ecosystems, especially in arid and semi-arid regions. A comparison study was carried out to verify when the artificial neural network (ANN) and multiple linear regression (MLR) models are appropriate for the prediction of soil organic matter (SOM) and particulate organic matter (POM). Discussions of advantages and disadvantages are given for both methods. Three different sets of easily available properties (soil properties alone, topographic and vegetation index, a combination of soil and topographic data) were used as inputs and the one affecting the model the most was determined. The smallest prediction errors were obtained by the ANN method; however, the prediction accuracies of the constructed MLR models using different data sets were closed to the ANN models in many cases. 相似文献
2.
现有关于盆栽控水模拟土壤干旱条件的试验中多采用含水率作为水分胁迫阈值,然而由于基质配比不同导致含水率相同的基质的水分状况也不尽相同,这导致各研究间结果难以对比和参考。为快速获取盆栽基质水分特征曲线,建立基质水分特征曲线预测模型。该研究以盆栽控水试验常用的泥炭土、蛭石和珍珠岩为基质材料,测定了不同配比基质的水分特征曲线,通过不同方法（多元回归模型、人工神经网络）建立了其预测模型。结果表明,人工神经网络模型对基质水分特征曲线的预测精度高于多元回归;相较于人工神经网络,多元回归模型的稳定性更高。综合考虑模型的精度和稳定性,多元回归模型是预测作物盆栽基质水分特征曲线的最佳模型。该模型为基质水分特征曲线快速获取以及相关作物干旱胁迫研究间的对比提供了方法和依据。 相似文献
3.
基于BP人工神经网络的长江河口地区土壤盐分动态模拟及预测 总被引：2，自引：1，他引：2
为开展长江河口地区土壤盐分动态的中长期模拟与预测,采用人工神经网络中应用较为成熟和广泛的BP网络建立长江河口地区土壤盐分与降雨量、蒸发量、长江水电导率、内河水电导率、地下水位、地下水电导率6因子间的非线性神经网络响应模型。网络模型结构为6-11-1,隐含层单元数用"试错法"确定。选择合适的参数训练和学习网络模型后,对河口地区2003年各月平均根层土壤电导率进行预测,并与线性回归模型预测结果进行比较。结果表明:BP网络模型较线性回归模型具有更高的预测精度,平均相对预测误差为7.3%,预测值与实测值相关性良好,可以满足实际应用需求。 相似文献
4.
Predicting Cationic Exchange Capacity in Calcareous Soils of East-Azerbaijan Province,Northwest Iran
Farrokh Asadzadeh Mahdi Maleki-Kakelar Farzin Shabani 《Communications in Soil Science and Plant Analysis》2019,50(9):1106-1116
The aim of this research is to study the efficiency of pedotransfer functions (PTFs) and artificial neural networks (ANNs) for cationic exchange capacity (CEC) prediction using readily available soil properties. Here, 417 soil samples were collected from the calcareous soils located in East-Azerbaijan province, northwest Iran and readily available soil properties, such as particle size distribution (PSD), organic matter (OM) and calcium carbonate equivalent (CCE), were measured. The entire 417 soil samples were divided into two groups, a training data set (83 soil samples) and test data set (334 soil samples). The performances of several published and derived PTFs and developed neural network algorithms using multilayer perceptron were compared, using a test data set. Results showed that, based on statistics of RMSE and R2, PTFs and ANNs had a similar performance, and there was no significant difference in the accuracy of the model results. The result of the sensitivity analysis showed that the ANN models were very sensitive to the clay variable (due to the high variability of the clay). Finally, the models tested in this study could account for 85% of the variations in cationic exchange capacity (CEC) of soils in the studied area.
Abbreviations: ANN: arti?cial neural networks; MLP: multilayer perceptron; MLR: multiple linear regression; PTFs: Pedotransfer Functions; RBF: Radial Basis Function; MAE: mean absolute error; MSE: mean square error; CEC: cationic exchange capacity 相似文献
5.
通过土壤微宇宙培养试验,研究了锯末尺寸、添加量和种类等因素对荧蒽特效降解菌MC(Mycobacterium flavescens)修复污染土壤(潮土、红壤、黑土、黄棕壤和水稻土)的效果.结果表明:锯末联合降解菌MC修复荧蒽污染的黄棕壤效果较好,优化条件下25 d荧蒽降解率为42.63％ ±1.05％;该联合修复对黑土和... 相似文献
6.
This paper examines whether multiple regression analysis and neural network models can be applied successfully for the indirect prediction of the runoff treatment performance with water quality indicator variables in an experimental storm water detention system rig. Five biologically mature experimental storm water detention systems with different designs treating concentrated gully pot liquor (spiked with dog droppings) were assessed. The systems were located on The King’s Buildings campus at The University of Edinburgh and were monitored for a period of 18 months. Multiple regression analyses indicated a relatively successful prediction of the biochemical oxygen demand and total suspended solids for most systems, but due to a relatively weak correlation between the predictors and both microbial indicators, multiple regression analyses were not applied for the prediction of intestinal enterococci and total coliform colony-forming units. However, artificial neural network models predicted microbial counts relatively well for most detention systems. 相似文献
7.
铬渣污染场地已经列为我国土壤污染重点治理对象,急需修复铬渣污染土壤的关键技术。本文通过室内模拟实验,采用振荡淋洗的方法研究了水、EDTA、EDDS、柠檬酸、草酸、盐酸、磷酸、环糊精和十二烷基苯磺酸钠等淋洗剂对铬渣污染场地Cr的淋洗效果,探讨了淋洗剂浓度、淋洗时间、土水比、淋洗次数等对淋洗效果的影响,并研究了不同淋洗剂复合对Cr的淋洗效果以及不同浓度柠檬酸淋洗前后重金属形态的变化。结果表明：水、EDTA、EDDS、环糊精和十二烷基苯磺酸钠对Cr的去除率较低,柠檬酸在浓度为0.5mol·L-1、土水比1：20、反应时间为24h、淋洗次数为2次的条件下可以达到最佳淋洗效果,Cr的去除率可达到82.8%;SDBS、EDTA与柠檬酸单独组合顺序或者混合淋洗,都没有增加柠檬酸对Cr的去除率。重金属形态分析表明,柠檬酸淋洗有效地改变了Cr的形态从而达到较高的修复效果。当柠檬酸浓度小于0.25mol·L-1时,对铬的去除主要以C（rⅥ）为主;当柠檬酸浓度大于0.25mol·L-1时,对铬的去除主要以C（rⅢ）为主。本文的研究结果为异位淋洗修复铬渣污染土壤提供理论依据。 相似文献
8.
Bert van Bavel 《Journal of Soils and Sediments》2006,6(4):208-214
Background, Aim and Scope
Polycyclic aromatic hydrocarbons (PAHs) are formed as a result of incomplete combustion and are among the most frequently
occurring contaminants in soils and sediments. PAHs are of great environmental concern due to their ubiquitous nature and
toxicological properties. Consequently, extensive research has been conducted into the development of methods to remediate
soils contaminated with PAHs. Fenton's reagent or ozone is the most commonly studied chemical oxidation methods. However,
the majority of remediation studies use soils that have been artificially contaminated with either one or a limited number
of PAH compounds in the laboratory. Hence, it is essential to extend such studies to soils contaminated with multiple PAHs
under field conditions.
Objectives The objective of this study is to investigate the capacity of Fenton's reagent and ozone to degrade PAHs in soils. The soils
have been collected from a number of different industrial sites and, therefore, will have been exposed to different PAH compounds
in varying concentrations over a range of time periods. The capacity of Fenton's reagent and ozone to degrade PAHs in industrially
contaminated soils is compared to results obtained in studies using soils artificially contaminated with PAHs in the laboratory.
Materials and Methods:
Nine soil samples, contaminated with PAHs, were collected from five different industrial sites in Sweden. For the Fenton's
reagent procedure, the pH of the soil slurry samples was adjusted to pH 3 and they were kept at a constant temperature of
70oC whilst H2O2 was added. For the ozone procedure, soil samples were mixed with 50% water and 50% ethanol and kept at a
constant temperature of 45 oC. Ozone was then continually introduced to each soil sample over a period of four hours. Following
the Fenton's reagent and ozone oxidation procedures, the samples were filtered to isolate the solid phase, which was then
extracted using pressurized liquid extraction (PLE). The sample extracts were cleaned up using open columns and then analysed
by gas chromatography-mass spectrometry (GC-MS).
Results:
The relative abundance of the detected PAHs varied between soils, associated with different industries. For example, low molecular
weight (LMW) PAHs were more abundant in soil samples collected from wood impregnation sites and high overall PAH degradation
efficiencies were observed in soils originating from these sites. In the contaminated soils studied, PAHs were more effectively
degraded using Fenton's reagent (PAH degradation efficiency of 40-86%) as opposed to ozone (PAH degradation efficiency of
10-70%). LMW PAHs were more efficiently degraded, using ozone as the oxidizing agent, whereas the use of Fenton's reagent
resulted in a more even degradation pattern for PAHs with two through six fused aromatic rings.
Discussion:
The degradation efficiency for both methods was largely dependent on the initial PAH concentration in the soil sample, with
higher degradation observed in highly polluted soils. LMW PAHs are more susceptible to degradation than high molecular weight
(HMW) PAHs. As a result of this the relative abundance of large (often carcinogenic) PAHs increased after chemical oxidation
treatment, particularly after ozone treatment. Repeated Fenton's reagent treatment did not result in any further degradation
of soil PAHs, indicating that residual soil PAHs are strongly sorbed. The effectiveness of the two oxidation treatment approaches
differed between industrial sites, thus highlighting the importance of further research into the influence of soil properties
on the sorption capacity of PAHs.
Conclusions:
This study demonstrates that the degree to which chemical oxidation techniques can degrade soil bound PAHs chemical degradation
is highly dependent on both the concentration of PAHs in the soils and the compounds present, i.e. the various PAH profiles.
Therefore, similarities in the PAH degradation efficiencies in the nine soil samples studied were observed with the two chemical
oxidation methods used. However, the degradation performance of Fenton's reagent and ozone differed between the two methods.
Overall, Fenton's reagent achieved the highest total PAH degradation due to stronger oxidation conditions. LMW PAHs showed
higher susceptibility to oxidation, whereas high molecular weight (HMW) PAHs appear to be strongly sorbed to the soils and
therefore less chemically available for oxidation. This study highlights the importance of including soils collected from
a range of contaminated sites in remediation studies. Such soil samples will contain PAH contaminants of varying concentrations,
chemical and physical properties, and have been aged under field conditions. In addition to the chemical and physical properties
of the soils, these factors will all influence the chemical availability of PAHs to oxidation.
Recommendations and Perspectives:
We recommend including aged contaminated soils in chemical degradation studies. In future chemical remediation work, we intend
to investigate the potential influence of the chemical and physical properties of PAHs and soil parameters potential influence
on the chemical oxidation efficiency in aged contaminated soils.
Due to the vast number of contaminated sites there is a great need of efficient remediation methods throughout the world.
This study shows the difficulties which may be experienced when applying remediation methods to a variation of contaminated
sites. 相似文献
9.
《Communications in Soil Science and Plant Analysis》2012,43(17):2123-2139
ABSTRACTThe traditional methods for the measurement of soil cation exchange capacity (CEC) are time-consuming and laborious. It is also difficult to maintain stability for long-term experiments and projects. Therefore, it is necessary to develop an indirect approach such as pedotransfer functions (PTFs) to estimate this property from more easily available soil data. The aim of this study was to compare multiple linear and nonlinear regression, classification and regression trees (C&RT), artificial neural network (ANN) model included multiple layer perceptron (MLP) and k-nearest neighbors (k-NN) to develop PTFs for predicting soil CEC. Soil samples, 929, were used into two subsets for training and testing of the models. Sensitivity and statistical analyzes were conducted to determine the most and the least influential variables affecting soil CEC. The prediction capability of models was assessed by statistical indicators included the normalized root-mean-square error (NRMSE) and the coefficient of determination (R2). Results of the present investigation showed that the k-NN and ANN models had the ability to estimate soil CEC by computing easily measurable variables with a guarantee of authenticity, reliability, and reproducibility. Therefore, the results of this study provide a superior basis for predicting soil CEC and could be applied to other parts of the world with similar challenges. 相似文献
10.
持久性有机污染场地土壤淋洗法修复研究进展 总被引：10，自引：0，他引：10
持久性有机污染场地土壤淋洗法是污染场地土壤物化修复方法中一种常用的技术。淋洗法是指运用特定淋洗剂对污染土壤进行深度洗涤,通过分离净化淋洗剂,实现回用集成,达到去除土壤中污染物的目的,并最终安全化处置污染物和修复土壤的过程。本文根据污染场地土壤处理位置、淋洗剂种类和淋洗剂施用方式的差异,将持久性有机污染场地土壤淋洗法划分为不同的种类;总结了为达到高效去除土壤中污染物质,可运用多级淋洗方式、超声方式、电动力方式和化学氧化等方式实现强化修复效率;阐述了污染场地土壤质地、污染物性质、淋洗剂性质、淋洗条件优化以及淋洗剂回用效率等因素对淋洗修复整体效用的显著影响;同时指出了目前持久性有机污染场地土壤淋洗法存在的问题和今后国内外研究和应用的方向。综合考虑土壤淋洗修复技术适用范围和成本因素,认为淋洗法是一种较符合我国持久性有机污染场地土壤实情的修复技术,具有较强的针对性和较广泛的运用前景。 相似文献
11.
基于ANN技术和高光谱遥感的盐渍土盐分预测 总被引：15，自引：10，他引：5
土壤盐渍化是干旱、半干旱农业区主要的土地退化问题,及时、精准、动态地监测盐渍土盐分,对于治理、防治盐渍土和进行农业可持续发展至关重要。以松嫩平原西部长岭县为例,利用盐渍土高光谱数据构建盐渍土盐分遥感预测模型。电导法测得土壤盐量,用ASD高光谱仪野外采集高光谱数据,利用光谱导数变换选择能够表征盐渍土盐分信息的最佳波段,即550、720、760、820和940 nm。通过比较3层和4层72种不同神经网络结构,最终选择5-6-1 结构的3层神经网络预测盐渍土盐分（R2 = 0.895,RMSE = 0.089）。与传统回归相比（R2 = 0.81,RMSE = 0.25）,运用高光谱数据与人工神经网络方法相结合,能够提高盐渍土的预测精度,说明人工神经网络在构建光谱反射率与土壤参数关系研究中具有突出优势。 相似文献
12.
基于BP神经网络的土壤水力学参数预测 总被引：7，自引：1，他引：7
为了获取区域土壤水分和溶质运移模拟所需的土壤水力学参数,利用黄淮海平原曲周县的试验资料建立基于BP神经网络的土壤转换函数模型。本文采用土壤粒径分布、容重、有机质含量等土壤基本理化性质,来预测土壤饱和导水率Ks、饱和含水量sθ、残余含水量θr、以及van Genuchten公式参数α、n的对数形式ln(α)和ln(n),并与多元线性逐步回归方法进行比较。t检验结果表明,BP神经网络训练和预测得到的模拟值与实测值之间吻合很好,该方法具有较高的预测精度。通过对平均相对误差的比较,得出在粒径分布的基础上增加容重、有机质含量等输入项目,可以提高部分土壤水力学参数的预测精度,而有些参数的预测精度反而降低。以误差平方和为标准的比较结果表明,BP神经网络模型的预测效果总的来看要优于多元线性回归法。 相似文献
13.
Sebastian Krahe Rolf-Alexander Düring Johan A. Huisman Andreas L. Horn Stefan Gäth 《Water, air, and soil pollution》2006,172(1-4):221-237
Partition coefficients K P of nonylphenol (NP) in soil were determined for 193 soil samples which differed widely in content of soil organic carbon (SOC), hydrogen activity, clay content, and in the content of dissolved organic carbon (DOC). By means of multiple linear regression analysis (MLR), pedotransfer functions were derived to predict partition coefficients from soil data. SOC and pH affected the sorption, though the latter was in a range significantly below the pKa of NP. Quality of soil organic matter presumably plays an important but yet not quantified role in sorption of NP. For soil samples with SOC values less than 3 g kg?1, model prediction became uncertain with this linear approach. We suggest that using only SOC and pH data results in good prediction of NP sorption in soils with SOC higher than 3 g kg?1. Considering the varying validity of the linear model for different ranges of the most sensitive parameter SOC, a more flexible, nonlinear approach was tested. The application of an artificial neuronal network (ANN) to predict sorption of NP in soils showed a sigmoidal relation between K P and SOC. The nonlinear ANN approach provided good results compared to the MLR approach and represents an alternative tool for prediction of NP partitioning coefficients. 相似文献
14.
利用人工污染土壤,研究了高锰酸钾对4种不同土壤中菲和芘的氧化修复效果。结果表明,当高锰酸钾浓度为33.33mmol·L^-1时,土壤中菲和芘的氧化去除率达到最大。高锰酸钾氧化去除率不仅与高锰酸钾浓度有关,还与土壤性质和老化时间有关。土壤有机质含量的增加会降低高锰酸钾对土壤中菲和芘的氧化去除率;随着老化时间的增加,高锰酸钾的氧化去除率逐渐降低。老化40d后,4种土壤中菲和芘的氧化去除率显著降低,菲的氧化去除率在14%～67%之间,芘的氧化去除率在61%～84%之间。高锰酸钾氧化前后,4种土壤中有机质含量下降范围为0.77%～9.21%。从土壤有机质含量来看,高锰酸钾氧化修复多环芳烃污染土壤对土壤质量影响较小,具有较好的应用前景。 相似文献
15.
基于地形属性使用回归, 克里格和人工神经网络方法估算饱和导水率空间分布 总被引：6，自引：0，他引：6
Several methods,including stepwise regression,ordinary kriging,cokriging,kriging with external drift,kriging with varying local means,regression-kriging,ordinary artificial neural networks,and kriging combined with artificial neural networks,were compared to predict spatial variation of saturated hydraulic conductivity from environmental covariates.All methods except ordinary kriging allow for inclusion of secondary variables.The secondary spatial information used was terrain attributes including elevation,slope gradient,slope aspect,profile curvature and contour curvature.A multiple jackknifing procedure was used as a validation method.Root mean square error (RMSE) and mean absolute error (MAE) were used as the validation indices,with the mean RMSE and mean MAE used to judge the prediction quality.Prediction performance by ordinary kriging was poor,indicating that prediction of saturated hydraulic conductivity can be improved by incorporating ancillary data such as terrain variables.Kriging combined with artificial neural networks performed best.These prediction models made better use of ancillary information in predicting saturated hydraulic conductivity compared with the competing models.The combination of geostatistical predictors with neural computing techniques offers more capability for incorporating ancillary information in predictive soil mapping.There is great potential for further research and development of hybrid methods for digital soil mapping. 相似文献
16.
污染土壤修复基准的研究和相关标准的制定,对于耕地的保护和环境标准的国际接轨具有极其重要的意义。本文从阐述污染土壤修复基准的概念出发,对污染土壤修复基准的国内外研究进展进行了概述;与此同时,还对国际上污染土壤修复/清洁标准的现状进行了分析。最后,从我国农业环保存在的问题出发,对污染土壤修复基准这一重大研究课题进行了展望和呼吁。 相似文献
17.
Phosphate compounds of lead (Pb) are highly insoluble and their formation in contaminated soils would aid immobilization of Pb. The goal of the current research was to evaluate the immobilization of Pb by various treatments of phosphate rock on contaminated agricultural soils typical of Taiwan, and to determine the optimal amount of phosphate rock for use in field application. Samples of contaminated soil, each containing Pb concentrations ranging from 346 to 1873 mg kg?1 were collected from arable land near a ceramic products manufacturing factory. Both batch immobilization experiments and in situ remediation were completed using phosphate rock additives. Results of the batch experiments demonstrate that the phosphate rock was effective in reducing Pb extractable by 0.1 M HCl, with a minimum reduction of 33–97% after 8 days of reaction, for initial Pb concentrations up to 1873 mg kg?1. HCl-extractable Pb did not decrease after an additional 2-day reaction with a greater phosphate rock loading. It was also found that the reaction time had less effect on Pb immobilization than the amount of phosphate rock added. Results from in situ remediation experiments indicate that soil-extractable Pb was reduced by 93% (mean; range 85.2–97.2%), which is comparable with the results of the batch study. Additionally, the soil pH was increased from 6.25 (mean; range 5.96–6.76) to 7.2 (mean; range 6.92–7.53) after remediation. Based upon the HCl-extractable Pb content and the amount of phosphate rock added, various linear log-linear regression curves were obtained. These predictive equations have been used for field application. Our field results demonstrate that phosphate rocks have a potential to cost-effectively treat Pb-contaminated soils in Taiwan. 相似文献
18.
19.
固化/稳定化修复后土壤重金属稳定性及再活化研究进展 总被引：3，自引：1，他引：3
固化/稳定化技术是一种经济、有效、快捷的重金属污染主流修复技术,随着我国以风险管控为主导策略的土壤污染防治工作的推进,该技术正发挥着极其重要的作用。固化/稳定化技术处置后土壤中的重金属并未移除,存在再活化的风险。本文对固化/稳定化技术特点、修复效果评估方法、评价标准等进行了系统总结,概述了修复后重金属赋存形态、生物有效性、微观形态等特征,着重阐述了冻融、水环境和酸雨淋溶3类环境胁迫下重金属的再活化行为和影响因素。在此基础上,讨论了当前固化/稳定化修复后土壤和场地环境监管体系构建的现状、不足和发展需求,提出需注重修复后重金属环境行为、再活化定量化等研究方向。 相似文献
20.
采用盆栽试验方法,通过添加赤泥颗粒修复铅锌污染土壤,按照火焰原子吸收分光光度法测定不同时期种植韭菜的土壤中重金属的含量,分析赤泥颗粒对土壤中重金属的钝化行为与机理,确定赤泥颗粒对土壤修复和对韭菜生长促进最佳的添加量。结果表明,赤泥颗粒能缓释OH-,促进重金属铅、锌化学形态转化和抑制生物吸收。铅、锌污染土壤修复的最佳赤泥颗粒添加量为5%,此时,土壤中铅、锌的生物有效态含量在修复期内分别降低了41.03%、26.55%;结合铅锌污染土壤修复与韭菜生长影响,初步确定赤泥颗粒的最佳施用量为1%,此时,土壤中铅、锌的生物有效态含量在修复期内分别降低了24.81%、15.9%;赤泥颗粒对铅锌污染土壤的修复能力大小为铅〉锌。 相似文献